Representation
Can brain-body regulation be represented as a dynamical system that supports real-time inference?
Applied AI Research in
Affective Computing
Cogitos Labs is an early-stage R&D lab working at the intersection of AI and neurotechnology, currently focused on affective brain-computer interface systems. We are modelling how the brain regulates emotions, and building a real-time closed-loop biofeedback system for emotional regulation support.
Study of Brain's Self Regulation
Our first R&D program uses synchronized recordings of brain and body signals - EEG, heart rate, respiration - to build computational models of how they shift between regulatory states. We use contemplative practices like meditation and controlled breathing to create conditions where regulation is natural, deliberate, observable, and reproducible. Three questions drive the work.
Transition Markers
What physiological and neural markers signify transitions between regulatory states - and can these be detected with sufficient lead time to enable intervention?
Transfer to AI
What computational principles underlying the brain's self-regulation can be transferred to AI architectures to make them self-regulating?
Target Applications
Our research can translate into three areas of application, each building on the same underlying science.
Clinical Platform
A sensing and regulation system for clinical settings - using EEG, heart rate, and respiration - designed to support people dealing with stress disorders, anxiety, and attention difficulties.
Consumer Wearables
The same science, made accessible for everyday use. A lighter wearable for the general population, helping people build emotional resilience outside clinical settings.
Self-Regulating AI
The longer-horizon direction. AI architectures that monitor their own behaviour, detect when they drift from their intended values, and correct course - without external supervision.
How We Work
The core commitments that govern our experiments, computational modelling, architecture and systems development
Naturalistic observation
We study regulation as it actually occurs. Experimental conditions are designed with help of contemplative practices to ensure naturalistic observation.
Co-evolving design
Our experimental data feeds into our models. Our model output inturn reshapes our experiments. Science and engineering evolve together.
Reusable infrastructure
Everything we build - pipelines, protocols, tools, frameworks - is designed to be reusable. Useful not just for current R&D program, but for future programs as well.
Responsible governance
We follow informed consent and independent ethics oversight. Physiological data is anonymised and encrypted. We comply with India's DPDP Act 2023.
Founding Team
Raja Valiveti
Co-founder
Leads R&D direction, infrastructure design, computational modelling, AI architecture, and systems development.
IIT Kharagpur alumnus. 25+ years in technology, leading development and management of large-scale distributed systems and enterprise AI deployment.
Aruna
Co-founder
Leads experimental design, participant coordination, physiological data collection, and data governance.
PSG College of Technology alumna, Masters in Applied Electronics. Trained practitioner of Yoga.
Collaborate with us
We welcome conversations with researchers, clinicians, and organisations interested in affective computing, cognitive neuroscience, or brain-computer interface applications. Write to us about your interest and background.